←back to thread

AMD funded a drop-in CUDA implementation built on ROCm: It's now open-source

(www.phoronix.com)
1045 points mfiguiere | 5 comments | 12 Feb 24 14:00 UTC | HN request time: 0.012s | source
Show context
btown ◴[12 Feb 24 14:37 UTC] No.39345221[source]▶
Why would this not be AMD’s top priority among priorities? Someone recently likened the situation to an Iron Age where NVIDIA owns all the iron. And this sounds like AMD knowing about a new source of ore and not even being willing to sink a single engineer’s salary into exploration.

My only guess is they have a parallel skunkworks working on the same thing, but in a way that they can keep it closed-source - that this was a hedge they think they no longer need, and they are missing the forest for the trees on the benefits of cross-pollination and open source ethos to their business.

replies(14): >>39345241 #>>39345302 #>>39345393 #>>39345400 #>>39345458 #>>39345853 #>>39345857 #>>39345893 #>>39346210 #>>39346792 #>>39346857 #>>39347433 #>>39347900 #>>39347927 #
hjabird ◴[12 Feb 24 15:26 UTC] No.39345853[source]▶
The problem with effectively supporting CUDA is that encourages CUDA adoption all the more strongly. Meanwhile, AMD will always be playing catch-up, forever having to patch issues, work around Nvidia/AMD differences, and accept the performance penalty that comes from having code optimised for another vendor's hardware. AMD needs to encourage developers to use their own ecosystem or an open standard.
replies(13): >>39345944 #>>39346147 #>>39346166 #>>39346182 #>>39346270 #>>39346295 #>>39346339 #>>39346835 #>>39346941 #>>39346971 #>>39347964 #>>39348398 #>>39351785 #
kgeist ◴[12 Feb 24 15:48 UTC] No.39346182[source]▶
Intel embraced Amd64 ditching Itanium. Wasn't it a good decision that worked out well? Is it comparable?
replies(2): >>39346627 #>>39346836 #
1. teucris ◴[12 Feb 24 16:17 UTC] No.39346627[source]▶
In hindsight, yes, but just because a specific technology is leading an industry doesn’t mean it’s going to be the best option. It has to play out long enough for the market to indicate a preference. In this case, for better or worse, it looks like CUDA’s the preference.
replies(1): >>39346692 #
2. diggan ◴[12 Feb 24 16:22 UTC] No.39346692[source]▶
> It has to play out long enough for the market to indicate a preference

By what measures hasn't that happened already? CUDA been around and constantly improving for more than 15 years, and there is no competitors in sight so far. It's basically the de facto standard in many ecosystems.

replies(1): >>39347461 #
3. teucris ◴[12 Feb 24 17:13 UTC] No.39347461[source]▶
There haven’t been any as successful, but there have been competitors. OpenCL, DirectX come to mind.
replies(1): >>39347824 #
4. cogman10 ◴[12 Feb 24 17:41 UTC] No.39347824{3}[source]▶
SYCL is the latest attempt that I'm aware of. It's still pretty active and may just work as it doesn't rely on video card manufactures to work out.
replies(1): >>39348316 #
5. zozbot234 ◴[12 Feb 24 18:18 UTC] No.39348316{4}[source]▶
SYCL is the quasi-successor to OpenCL, built on the same flavor of SPIR-V. Various efforts are trying to run it on top of Vulkan Compute (which tends to be broadly support by modern GPU's) but it's non-trivial because the technologies are independently developed and there are some incompatibilities.